Automated detection of focal cortical dysplasia type II with surface‐based magnetic resonance imaging postprocessing and machine learning

• Published in: Epilepsia (Copenhagen) 2018-05, Vol.59 (5), p.982-992
• Main Authors: Jin, Bo, Krishnan, Balu, Adler, Sophie, Wagstyl, Konrad, Hu, Wenhan, Jones, Stephen, Najm, Imad, Alexopoulos, Andreas, Zhang, Kai, Zhang, Jianguo, Ding, Meiping, Wang, Shuang, Wang, Zhong Irene
• Format: Article
• Language: English
• Subjects: Adolescent; Adult; Area Under Curve; Artificial intelligence; Automation; Brain - diagnostic imaging; Child; Child, Preschool; Cortex; Dysplasia; Epilepsy; Epilepsy - diagnostic imaging; Female; focal cortical dysplasia; Hippocampus; Humans; Learning algorithms; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Malformations of Cortical Development, Group I - diagnostic imaging; Middle Aged; Morphometry; MRI postprocessing; Neural networks; Neuroimaging - methods; NMR; Nuclear magnetic resonance; ROC Curve; Sclerosis; Sensitivity and Specificity; surgery; Young Adult
• ISSN: 0013-9580; 1528-1167
• DOI: 10.1111/epi.14064

Summary Objective Focal cortical dysplasia (FCD) is a major pathology in patients undergoing surgical resection to treat pharmacoresistant epilepsy. Magnetic resonance imaging (MRI) postprocessing methods may provide essential help for detection of FCD. In this study, we utilized surface‐based MRI morphometry and machine learning for automated lesion detection in a mixed cohort of patients with FCD type II from 3 different epilepsy centers. Methods Sixty‐one patients with pharmacoresistant epilepsy and histologically proven FCD type II were included in the study. The patients had been evaluated at 3 different epilepsy centers using 3 different MRI scanners. T1‐volumetric sequence was used for postprocessing. A normal database was constructed with 120 healthy controls. We also included 35 healthy test controls and 15 disease test controls with histologically confirmed hippocampal sclerosis to assess specificity. Features were calculated and incorporated into a nonlinear neural network classifier, which was trained to identify lesional cluster. We optimized the threshold of the output probability map from the classifier by performing receiver operating characteristic (ROC) analyses. Success of detection was defined by overlap between the final cluster and the manual labeling. Performance was evaluated using k‐fold cross‐validation. Results The threshold of 0.9 showed optimal sensitivity of 73.7% and specificity of 90.0%. The area under the curve for the ROC analysis was 0.75, which suggests a discriminative classifier. Sensitivity and specificity were not significantly different for patients from different centers, suggesting robustness of performance. Correct detection rate was significantly lower in patients with initially normal MRI than patients with unequivocally positive MRI. Subgroup analysis showed the size of the training group and normal control database impacted classifier performance. Significance Automated surface‐based MRI morphometry equipped with machine learning showed robust performance across cohorts from different centers and scanners. The proposed method may be a valuable tool to improve FCD detection in presurgical evaluation for patients with pharmacoresistant epilepsy.